© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8291
    Prev
    Next
    INDEX
    Explanations

    programming class inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -2.00
     &
    -1.67
     then
    -1.63
     many
    -1.56
     found
    -1.52
     to
    -1.52
     in
    -1.52
     "
    -1.48
     also
    -1.39
     suitable
    -1.39
    POSITIVE LOGITS
     damska
    1.73
    lovely
    1.51
    weird
    1.41
     trám
    1.41
    actéristi
    1.40
    鍏
    1.38
    gebra
    1.38
     épaules
    1.36
     hoffe
    1.36
    hould
    1.36
    Activations Density 0.033%

    No Known Activations